KelleyYin

llama_index

LlamaIndex is a data framework for your LLM applications

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

insightface

State-of-the-art 2D and 3D Face Analysis Project

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

flash-attention

Fast and memory-efficient exact attention

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

text-generation-inference

Large Language Model Text Generation Inference

Llama2-Chinese

Llama中文社区，最好的中文Llama大模型，完全开源可商用

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

text2vec

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

wikiextractor

A tool for extracting plain text from Wikipedia dumps

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

chatglm.cpp

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & more LLMs

work-in-australia

Work in Australia as a Developer / 程序员如何申请到澳洲工作

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

FinGLM

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

papermage

library supporting NLP and CV research on scientific papers

CMMLU

CMMLU: Measuring massive multitask language understanding in Chinese

HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

RankGPT

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

healthcaredatastandard

healthcare data standard in China

hf_transfer

Multi-CPR

[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval

GPT-CLS-CARP

Code for the paper `Text Classification via Large Language Models`.

vllm-client

vLLM client with minimal dependencies

Semantic-Search